Author summary The gut wall is the first barrier that encounters orally absorbed drugs, and it substantially modulates the bioavailability of drugs and supports several classes of side effects. We developed context-specific metabolic models of the enterocyte constrained by drug-induced gene expression and trained a machine learning classifier using metabolic reaction rates as features to predict the occurrence of side effects. Additionally, we clustered the compounds based on their metabolic and transcriptomic features to find similarities between their physiological effects. Our work provides a better understanding of the compound physiological effects solely using in vitro data, which can further improve the translation of new chemical entities to clinical trials.